Related papers: The Last Mile to Production Readiness: Physics-Bas…
Real-time animation of virtual characters has traditionally been accomplished by playing short sequences of animations structured in the form of a graph. These methods are time-consuming to set up and scale poorly with the number of motions…
Many robotic tasks rely on the accurate localization of moving objects within a given workspace. This information about the objects' poses and velocities are used for control,motion planning, navigation, interaction with the environment or…
Embodied navigation holds significant promise for real-world applications such as last-mile delivery. However, most existing approaches are confined to either indoor or outdoor environments and rely heavily on strong assumptions, such as…
The levels of agility and flight or swimming performance demonstrated by insects, birds, fish, and even some aquatic invertebrates, are often vastly superior to what even the most advanced human-engineered vehicles operating in the same…
Motion forecasting is crucial in enabling autonomous vehicles to anticipate the future trajectories of surrounding agents. To do so, it requires solving mapping, detection, tracking, and then forecasting problems, in a multi-step pipeline.…
Human action recognition and analysis have great demand and important application significance in video surveillance, video retrieval, and human-computer interaction. The task of human action quality evaluation requires the intelligent…
Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…
Calibrating a robot simulator's physics parameters (friction, damping, material stiffness) to match real hardware is often done by hand or with black-box optimizers that reduce error but cannot explain which physical discrepancies drive the…
Computer vision is largely based on 2D techniques, with 3D vision still relegated to a relatively narrow subset of applications. However, by building on recent advances in 3D models such as neural radiance fields, some authors have shown…
We introduce an approach for augmenting text-to-video generation models with customized motions, extending their capabilities beyond the motions depicted in the original training data. By leveraging a few video samples demonstrating…
Animating stylized characters to match a reference motion sequence is a highly demanded task in film and gaming industries. Existing methods mostly focus on rigid deformations of characters' body, neglecting local deformations on the…
High-fidelity motion tracking serves as the ultimate litmus test for generalizable, human-level motor skills. However, current policies often hit a "generality barrier": as motion libraries scale in diversity, tracking fidelity inevitably…
This paper presents a method for constrained motion planning from vision, which enables a robot to move its end-effector over an observed surface, given start and destination points. The robot has no prior knowledge of the surface shape,…
Computer vision for animals holds great promise for wildlife research but often depends on large-scale data, while existing collection methods rely on controlled capture setups. Recent data-driven approaches show the potential of…
One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…
Generic motion understanding from video involves not only tracking objects, but also perceiving how their surfaces deform and move. This information is useful to make inferences about 3D shape, physical properties and object interactions.…
Motion plays a crucial role in understanding videos and most state-of-the-art neural models for video classification incorporate motion information typically using optical flows extracted by a separate off-the-shelf method. As the…
Despite recent advances in image-to-video generation, better controllability and local animation are less explored. Most existing image-to-video methods are not locally aware and tend to move the entire scene. However, human artists may…
Recent progress in robot learning has been driven by large-scale datasets and powerful visuomotor policy architectures, yet policy robustness remains limited by the substantial cost of collecting diverse demonstrations, particularly for…
Human motion generation involves creating natural sequences of human body poses, widely used in gaming, virtual reality, and human-computer interaction. It aims to produce lifelike virtual characters with realistic movements, enhancing…